Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    adjectives describing various qualities or characteristics

    oai_token-act-pair · gpt-3.5-turbo

    the word "rather" and its context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elsen
    -0.87
    iliate
    -0.83
    ULTS
    -0.78
    illary
    -0.76
    Reviewed
    -0.74
    ulkan
    -0.73
    uay
    -0.73
    adium
    -0.73
    ividual
    -0.71
    rats
    -0.70
    POSITIVE LOGITS
     pathetic
    1.01
     than
    0.97
     amusing
    0.97
     pricey
    0.93
     pointless
    0.92
     tame
    0.91
     ironic
    0.91
     inconvenient
    0.90
     boring
    0.90
     cryptic
    0.89
    Act Density 0.025%

    No Known Activations